KVBench (Brief Caption) - Biology (Chinese): leaderboard
KVBench (2026) tests whether text-to-image models can draw correct senior high-school biology content, such as diagrams and scientific illustrations, from Chinese prompts given as a brief caption, so the model must supply the textbook knowledge itself. Qwen2.5-VL-32B checks each image against a list of textbook-grounded constraints; the score is the percentage satisfied, higher is better.
Metric: Checklist score (%) on the biology prompts in Chinese, each given as a brief caption, so the model must supply the textbook knowledge itself: KVBench knowledge-intensive text-to-image prompts from over 30 senior high-school textbooks (150 per subject and language, each with a textbook reference image); Qwen2.5-VL-32B-Instruct answers a checklist of four to six binary questions (key objects, attributes, spatial relations, reasoning outcomes) about each generated image, and the score is the mean share of satisfied items, in percent; higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 14 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Nano Banana Pro (Gemini 3 Pro Image) | 69.35 | |
| 2 | Seedream 4.0 | 44.98 | |
| 3 | FLUX.2-dev | 42.82 | |
| 4 | GPT-Image (KVBench checkpoint unspecified) | 38 | |
| 5 | FLUX 2 Max | 22.8 | |
| 6 | OmniGen2 | 17.76 | #4579 |
| 7 | Qwen-Image | 14.76 | |
| 8 | BAGEL-7B-MoT | 14.13 | #4619 |
| 9 | Z-Image | 13.11 | |
| 10 | FLUX.1-dev | 10.91 | |
| 11 | SD3.5-Large (KVBench GGUF build, quantization unspecified) | 10.09 | |
| 12 | FLUX.1-Krea-dev | 7.93 | |
| 13 | Janus-Pro | 6.64 | |
| 14 | Show-o2 | 5.93 |
Interactive version: theaggregate.ai/benchmark?slug=kvbench-brief-caption-biology-chinese · How It Works · Data refreshed daily, snapshot 2026-11-21.